Individual skill
swimsuit-live-portraits
一句话制作泳装动态立绘视频合集:用 ComfyUI 生成指定角色的首帧,逐张用本地 MiniMax H3 I2V 生成有自然声的片段,再按 8 段约一分钟的真实节奏剪辑;支持换角色、动作、场景和 BGM,包含任务恢复与原声混音。
templates/character-showcase/swimsuit-live-portraits/SKILL.md
Source commit 47cc68e1fe7a04213eb9aa53db9f08cb9a06d317
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- Yes
- Observed behavior
- Instructions only
- Last checked
- Nov 11, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 9
- Repository last updated
- Sep 18, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent-skills Repository topic
- anime Repository topic
- comfyui Repository topic
- minimax-h3 Repository topic
- video-generation Repository topic
- video-recipes Repository topic
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
LICENSEasset · 1,088 bytesLICENSES.mddoc · 1,248 bytesREADME.mddoc · 1,606 bytesSKILL.mdcore · 7,648 bytesexamples/README.mddoc · 1,633 bytesexamples/edit-with-bgm.jsonasset · 2,390 bytesexamples/edit.jsonasset · 2,254 bytesexamples/eight-shot-plan.jsonasset · 11,037 bytesexamples/request.example.jsonasset · 906 bytesprofile.jsonasset · 2,844 bytesprompts/first-frame.template.txtdoc · 899 bytesprompts/h3.template.txtdoc · 1,045 bytesreferences/editing.mddoc · 2,437 bytesreferences/evidence.mddoc · 2,480 bytesreferences/generation.mddoc · 5,432 bytesreferences/shot-plan.mddoc · 2,245 bytesreferences/validation.mddoc · 1,151 bytessources.mddoc · 896 bytesworkflows/toolkit-source.jsonasset · 751 bytes
Read excerpt
# 泳装动态立绘视频集
按下面顺序完成首帧、动态片段和成片。本子模板默认 8 镜头、保留自然声;其他环境和恢复规则继承[角色视频合集](../video-collection/SKILL.md)的环境、队列与交付流程,后期调用[角色展示剪辑](../../../skills/character-showcase-editing/SKILL.md)。当前模板所在目录至仓库根为 `../../..`。
## 1. 把一句话落成项目
将 [request.example.json](examples/request.example.json) 复制为用户项目的请求记录。记录角色、固定外观、场景、图像后端、BGM 路径和输出目录;将角色身份与每个镜头分别保存,避免同一角色在不同镜头变脸或换装。
- 用户指定一个角色:替换全部 8 个角色槽;多个角色:按用户顺序分配,没有顺序时均匀分配并记录。
- 用户已经提供首帧:按镜头绑定,补生成缺少的张数。只提供身份图:据此准备各镜头首帧,不能把一张立绘冒充 8 个不同场景。
- 未给角色:复用用户当前项目角色;没有项目身份时询问想使用的角色;用户选择原创时再设计统一的成年角色外观。
- 默认采用 [8 段计划](examples/eight-shot-plan.json)的动作与剪辑范围,约 62.15 秒。角色不具备机械配件时,第 4 段改成普通发饰随风运动,保留害羞和卡通表情的时间顺序。
- 未给 BGM:保留 H3 自然声,不自动取用示例案例歌曲。只要求重剪现成片段时跳过生成,交付明确标为重剪。